chore: mise à jour output pipeline (anonymized + structured)

Résultats de re-traitement pipeline v2 sur 261 dossiers.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
dom
2026-03-07 23:14:42 +01:00
parent c73515ac89
commit 13fe9fa666
734 changed files with 157158 additions and 304963 deletions

View File

@@ -0,0 +1,57 @@
{
"source_file": "LETTRE DE SORTIE 23087691.pdf",
"total_replacements": 38,
"regex_replacements": 16,
"ner_replacements": 8,
"sweep_replacements": 14,
"entities_found": [
{
"original": "Madame Jacqueline OROS",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.8998494148254395
},
{
"original": "Lambert-Eaton",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9570108652114868
},
{
"original": "Guyon",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8444855809211731
},
{
"original": "Mingazzini",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9984346628189087
},
{
"original": "Sandrine",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9405206441879272
},
{
"original": "Sandrine",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.8752485513687134
},
{
"original": "Les Embruns",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9638642072677612
},
{
"original": "OROS",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9211885929107666
}
]
}

View File

@@ -0,0 +1,375 @@
{
"source_file": "trackare-11011389-23087691_11011389_23087691.pdf",
"total_replacements": 439,
"regex_replacements": 242,
"ner_replacements": 14,
"sweep_replacements": 183,
"entities_found": [
{
"original": "11011389",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11011389",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11011389",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11011389",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11011389",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11011389",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11011389",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11011389",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11011389",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11011389",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11011389",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11011389",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11011389",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11011389",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11011389",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11011389",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11011389",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11011389",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "11011389",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23087691",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23087691",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23087691",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23087691",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23087691",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23087691",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23087691",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23087691",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23087691",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23087691",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23087691",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23087691",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23087691",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23087691",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23087691",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23087691",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23087691",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23087691",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23087691",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "99999",
"replacement": "[LIEU_NAISS_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "LOURDES",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "FLABEAU Olivier",
"replacement": "[MEDECIN_5]",
"source": "regex",
"category": "patient"
},
{
"original": "OROS",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "OROS",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "JACQUELINE",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "JACQUELINE",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "CENTRE DE REEDUCATION LES EMBRUNS Ville de résidence: BIDART",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "JAOUEN",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9691097736358643
},
{
"original": "RODRIGUEZ Lucas",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9960408806800842
},
{
"original": "PAILLOUX Sylvie",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.986483097076416
},
{
"original": "PAILLOUX Sylvie",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9786239862442017
},
{
"original": "FLABEAU Olivier",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9758527278900146
},
{
"original": "MONTELUKAST",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9609597325325012
},
{
"original": "MEST",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9030250310897827
},
{
"original": "PAILLOUX Sylvie",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9605965614318848
},
{
"original": "PAILLOUX Sylvie",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.9806697964668274
},
{
"original": "FLABEAU Olivier",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.994556188583374
},
{
"original": "FLABEAU Olivier Signé",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.8733415603637695
},
{
"original": "Sylvie Signé",
"replacement": "[SOIGNANT_11]",
"source": "ner",
"score": 0.8343669772148132
},
{
"original": "Mingazzini",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9857470989227295
},
{
"original": "Mingazzini",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.8191893696784973
}
]
}